Aircraft Wake Recognition and Strength Classification Based on Deep Learning

Abstract

Aircraft wake is a pair of counter-rotating vortices generated behind the aircraft, which can greatly impact the safety of fast takeoff and landing of aircraft and limit the improvement of airport capacity. The current wake parameter retrieval methods cannot locate the wake vortex's position and estimate its strength level in real time. To deal with this issue, a novel algorithm based on YOLOv5s deep learning network is proposed. The new algorithm establishes single vortex locating concept to adapt the wake vortex's evolution at complicate background wind field conditions, and proposes strength-based classification standard which can represent the real-time hazard of wake vortex to shorten the takeoff and landing intervals. Meanwhile, EIOU loss function is introduced to improve the precision of YOLOv5s network. Compared with the state-of-theart object detection approaches, such as Cascade R-CNN, FCOS, and YOLOv5l, the superiority of new method is demonstrated in terms of accuracy and robustness by using the field detection data from Hong Kong International Airport.

A comprehensive survey of existing approaches for close parallel runway landing operations: toward identifying the optimal method

“…The wake safety limit for very closely spaced parallel runway operations refers to the minimum distance that must be maintained between aircraft taking off or landing on parallel runways to ensure safe separation and prevent the effects of wake turbulence. Aircraft wake refers to the creation of two opposing vortices behind an aircraft, which can have significant implications for the safe execution of quick takeoffs and landings, as well as restrict advancements in airport capacity [6].…”